Research archive

Publications.

Language models, evidence, and human-centered AI.

Google Scholar

By year · newest first13 publications

2026

Method summary

JCDL 2026

Can LLMs Reason Over Where and When? Benchmarking Spatiotemporal Synthesis in Crisis Response

Sawyer Alston, Yashaswini Sreenivasa Shetty, Sreeja Kanuganti, Anirban Saha Anik, Xiaoying Song, and Lingzi Hong

Paper Project page Cite

Figure 2. Overview of the RO-PnR framework.

Method diagram

EMNLP 2026

Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention

Xiaoying Song, Anirban Saha Anik, Jinyu Liu, Qitao Tan, Geng Yuan, and Lingzi Hong

Paper Project page Cite

Figure 1. SciClaimSeekers system architecture.

Method diagram

CLEF 2026 Working Notes

SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking

Mohotarema Rashid, Nansu Baniya, Anirban Saha Anik, Xiaoying Song and Lingzi Hong

Paper Project page Cite

Method summary

CLEF 2026 Working Notes

SourceMinds at CheckThat! 2026: NLI-Grounded Citation Auditing in a Multi-Agent Pipeline for Full Fact-Checking Article Generation

Farhan Sharukh Hasan, Anirban Saha Anik, Eric Liu, Xiaoying Song, Mohotarema Rashid and Lingzi Hong

Paper Project page Cite

Method summary

CLEF 2026 Working Notes2nd place

VeriFind at CheckThat! 2026: Enhancing Numerical Claim Verification via Fine-Tuned LLMs

Diana Zhang, Xiaoying Song, Mohotarema Rashid, Anirban Saha Anik, Junhua Ding, and Lingzi Hong

Paper Project page Cite

2025

Figure 1. Multi-agent retrieval-augmented framework for health misinformation.

Method diagram

COLM 2025Runner-up

Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation

Anirban Saha Anik, Xiaoying Song, Elliott Wang, Bryan Wang, Bengisu Yarimbas, and Lingzi Hong

Paper Project page Cite

Figure 2. Controlled-Literacy counterspeech generation framework.

Method diagram

EMNLP 2025Finalist

Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL

Xiaoying Song, Anirban Saha Anik, Dibakar Barua, Pengcheng Luo, Junhua Ding, and Lingzi Hong

Paper Project page Cite

Figure 2. Overview of the dynamic fusion framework.

Method diagram

EMNLP 2025

A Dynamic Fusion Model for Consistent Crisis Response

Xiaoying Song, Anirban Saha Anik, Eduardo Blanco, Vanessa Frías-Martínez, and Lingzi Hong

Paper Project page Cite

Simplified comparison of independent ClaimIQ approaches: selected evidence is used with zero-shot prompted LLaMA or fine-tuned LoRA LLaMA and RoBERTa models, each predicting True, False or Conflicting.

Method summary

CLEF 2025 Working Notes

ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims

Anirban Saha Anik, Md Fahimul Kabir Chowdhury, Andrew Wyckoff, and Sagnik Ray Choudhury

Paper Project page Cite

Method diagram

ISCRAM 2025

Dynamic Fusion of Large Language Models for Crisis Communication

Xiaoying Song, Anirban Saha Anik, Vanessa Frías-Martínez, and Lingzi Hong

Paper Project page Cite

2024

Method summary

ICCIT 2024

Outcome-Based Education: Evaluating Students' Perspectives Using Transformer

Shuvra Smaran Das, Anirban Saha Anik, Md. Kishor Morol, and Mohammad Sakib Mahmood

Paper Project page Cite

2023

Method summary

NCIM 2023

A Study on Future Lockdown Predictions Using ANN

Shuvra Smaran Das, Anirban Saha Anik, Md. Muzakker Hossain, Md. Kishor Morol, Fariha Jahan, and Md. Abdullah Al-Jubair

Paper Project page Cite

2022

Figure 1. Methodology for COVID-19 chest X-ray classification using EfficientNet variants.

Method diagram

ICRPSET 2022

A Comparative Analysis for the Detection of COVID-19 from Chest X-ray Dataset

Anirban Saha Anik, Kowshik Chakraborty, Bishowjit Datta, Abdul Kader, and Md. Kishor Morol

Paper Project page Cite

2026

2025

2024

2023

2022

No matching publications